Ophthalmic Images Research Articles

Ophthalmic image acquired by ophthalmologists and by allied health personnel as part of a telemedicine strategy: a comparative study of image quality.

This study evaluates the quality of ophthalmic images acquired by a nurse technician trained in teleophthalmology as compared with images acquired by an ophthalmologist, in order to provide a better understanding of the workforce necessary to operate remote care programs. A cross-sectional study was performed on 2044 images obtained from 118 participants of the TeleOftalmo project, in Brazil. Fundus and slit-lamp photography were performed on site by an ophthalmologist and by a nurse technician under the supervision of a remote ophthalmologist. Image quality was then evaluated by masked ophthalmologists. Proportion of suitable images in each group was compared. The proportion of concordant classification regarding quality was 94.8%, with a corrected kappa agreement of 0.94. When analyzing each type of photo separately, there was no significant difference in the proportion of suitable images between on-site ophthalmologist and nurse technician with remote ophthalmologist assistance for the following: slit-lamp views of the anterior segment and anterior chamber periphery, and fundus photographs centered on the macula and on the optic disc (P = 0.825, P = 0.997, P = 0.194, and P = 0.449, respectively). For slit-lamp views of the lens, the proportion of suitable images was higher among those obtained by an ophthalmologist (99.6%) than by a technician (93.8%, P < 0.01). Ophthalmic photographs acquired by a trained technician consistently achieved >90% adequacy for remote reading. Compared with ophthalmologist-acquired photos, the proportion of images deemed suitable achieved a high overall agreement. These findings provide favorable evidence of the adequacy of teleophthalmological imaging by nurse technicians.

Deep OCT image compression with convolutional neural networks.

We report an end-to-end image compression framework for retina optical coherence tomography (OCT) images based on convolutional neural networks (CNNs), which achieved an image size compression ratio as high as 80. Our compression scheme consists of three parts: data preprocessing, compression CNNs, and reconstruction CNNs. The preprocessing module was designed to reduce OCT speckle noise and segment out the region of interest. Skip connections with quantization were developed and added between the compression CNNs and the reconstruction CNNs to reserve the fine-structure information. Two networks were trained together by taking the semantic segmented images from the preprocessing module as input. To train the two networks sensitive to both low and high frequency information, we leveraged an objective function with two components: an adversarial discriminator to judge the high frequency information and a differentiable multi-scale structural similarity (MS-SSIM) penalty to evaluate the low frequency information. The proposed framework was trained and evaluated on ophthalmic OCT images with pathological information. The evaluation showed reconstructed images can still achieve above 99% similarity in terms of MS-SSIM when the compression ratio reached 40. Furthermore, the reconstructed images after 80-fold compression with the proposed framework even presented comparable quality with those of a compression ratio 20 from state-of-the-art methods. The test results showed that the proposed framework outperformed other methods in terms of both MS-SSIM and visualization, which was more obvious at higher compression ratios. Compression and reconstruction were fast and took only about 0.015 seconds per image. The results suggested a promising potential of deep neural networks on customized medical image compression, particularly valuable for effective image storage and tele-transfer.

MO002OPHTHALMOLOGICAL EFFECTS OF ROXADUSTAT IN THE TREATMENT OF ANAEMIA IN CHRONIC KIDNEY DISEASE PATIENTS ON DIALYSIS IN A PHASE 3, RANDOMISED, DOUBLE-BLIND, ACTIVE-COMPARATOR CONVERSION STUDY

Abstract Background and Aims Roxadustat is an orally administered hypoxia-inducible factor prolyl hydroxylase inhibitor (HIF-PHI) approved in China for the treatment of dialysis-dependent (DD) and non–dialysis-dependent chronic kidney disease (CKD) anaemia, and in Japan for the treatment of DD CKD anaemia. An acceptable safety profile as well as noninferiority of roxadustat to darbepoetin alfa (DA), measured by haemoglobin (Hb) change from baseline (BL), was shown in patients (pts) with DD CKD in a Japanese phase 3, randomised double-blind, double-dummy study (CL-0307). Some nonclinical data suggest that HIF stimulation may promote angiogenesis, thereby increasing the risk of certain retinal pathologies. As such, this report focuses on a prospective analysis of ophthalmological/retinal-related events observed during the 24-week study period of the aforementioned phase 3 study. Method Japanese pts with DD CKD were randomised 1:1 to receive roxadustat three times weekly or DA once weekly; doses were titrated to maintain Hb between 10–12 g/dL. Ophthalmological/retinal-related outcomes were evaluated in pts who received ≥1 dose of study drug (SAF) and included emergence of adverse events assessed by the investigator and ophthalmological findings based on assessments performed by centralised grading. Ophthalmic imaging (colour fundus photography, optical coherence tomography) and assessment of visual acuity were performed at BL, Week 12, and Week 24 or at study discontinuation according to Ophthalmic Image Acquisition Guidelines. Each investigator evaluated the ophthalmic images and assessed the clinical relevance of any changes. Central evaluation of ophthalmological examination results was then performed by two independent specialists who were blinded to study treatment. During central evaluation, the reviewers assessed ophthalmic images in accordance with the Safety Independent Ophthalmology Review Charter. If graders’ results disagreed, adjudication was performed by a blinded, independent grader who did not participate in the primary review of the patient data. Grading results and visual acuity were analysed descriptively. Results In the SAF, a total of 302 pts were randomised to receive either roxadustat (n=150) or DA (n=152). At BL, previous or concurrent retinal vascular disorders were present in 41.3% (62/150) and 37.5% (57/152) of pts in the roxadustat and DA groups, respectively; 32.7% (49/150) and 27.6% (42/152) of pts presented with a history of both diabetes mellitus and retinal vascular disorders, respectively. The mean (SD) duration of exposure to study drug was 146.7 (45.8) days in the roxadustat group and 154.7 (37.4) days in the DA group. The proportion of pts with new or worsening retinal haemorrhages during the treatment period was 32.4% (n=46/142) with roxadustat and 36.6% (n=53/145) with DA. In a subgroup analysis of pts with no retinal haemorrhage at BL, the proportion of pts with new retinal haemorrhages was 19.1% (n=18/94) with roxadustat and 25.0% (n=24/96) with DA during the treatment period; in pts with ≥1 retinal haemorrhage at BL, the proportion of pts with new or worsening retinal haemorrhages was 58.3% (n=28/48) with roxadustat and 59.2% (n=29/49) with DA during the treatment period. From BL, no clinically meaningful changes in visual acuity or retinal thickness were found in either treatment group. Similarly, from BL, no clinically meaningful changes were found in the proportion of pts exhibiting intra-/sub-retinal fluid, hard exudates, or cotton wool spots in either treatment group. Conclusion These findings suggest that, during the 24-week treatment period, DD CKD pts treated with roxadustat were not at an increased risk of ophthalmic abnormalities—including retinal haemorrhages or increased retinal thickness—compared with pts treated with DA.

Retina–electrode interface properties and vision restoration by two generations of retinal prostheses in one patient—one in each eye

Objective. The Argus I implant is a first-generation epiretinal prosthesis approved for an investigational clinical trial in the U.S. Its successor, the Argus II implant, has a higher electrode density for increased spatial resolution and covers a larger retinal area to accommodate a wider visual angle. Both generations of Argus restored some vision to end-stage RP patients, but it remains unclear how the increased electrode count affected the visual percepts. Here we report a study of the first person on earth with two ‘bionic eyes’, with an Argus I implanted in one eye and Argus II in the other, to compare the retina–electrode interface and the visual outcome of the two devices. Approach. The retina–electrode interface was examined by electrode impedance, perceptual threshold, and ophthalmic images such as ocular coherence tomography data and fundus imaging. The subject’s visual outcomes were evaluated by computer-based visual function tests and subjective feedback. Main results. The electrode impedance of both Argus I and II slowly decreased overtime after implantation, accompanied by a gradual increase in the perceptual threshold. A quantitative analysis of the impedance and retina–electrode distance revealed somewhat different causes of impedance change in Argus I vs. II. Evaluation of the visual functions restored and feedback from the subject suggest that the Argus II device enables improved spatial visual ability over Argus I, but adaptation to prosthetic vision did not lead to a measurable performance improvement in the standard visual function tests. Significance. This study of Argus I and II in the same subject directly compares for the first time the interface properties and prosthetic vision in two eyes that share the same disease mechanism and converged visual pathway in higher visual centers, offering exciting new insights into the influence of the electrode parameters and layout to prosthetic vision.Trial registration: Data collected within clinical trials registered at NIH (NCT00279500 & NCT01860092).

A Density and Reliability Guided Aggregation for the Assessment of Vessels and Nerve Fibres Tortuosity

The tortuosity assessment of vessels and nerve fibres in ophthalmic images has drawn substantial attention, for its potentials in assisting various medical diagnoses. Numerous morphological tortuosity measures have been leveraged to quantify tortuosity from various perspectives, which warrants the simultaneous use of multiple measures with an aim to produce a robust and accurate assessment. This paper proposes an approach for the automated assessment of curvilinear structures’ tortuosity. Starting with the generation of clusters of tortuosity density for each individual measure, labelled fuzzy sets are then extracted that enhances the readability of subsequent operations. Finally, results from multiple measures are aggregated by a nearest neighbour guided approach where weights are generated in a data-driven manner to explain the derived aggregations. Experimental results on both ophthalmic vessel and nerve images demonstrate the superior performance of the proposed method over those where measurements are used independently or aggregated using conventional averaging operators.

A Systematic Review of Deep Learning Methods Applied to Ocular Images

Artificial intelligence is having an important effect on different areas of medicine, and ophthalmology has not been the exception. In particular, deep learning methods have been applied successfully to the detection of clinical signs and the classification of ocular diseases. This represents a great potential to increase the number of people correctly diagnosed. In ophthalmology, deep learning methods have primarily been applied to eye fundus images and optical coherence tomography. On the one hand, these methods have achieved an outstanding performance in the detection of ocular diseases such as: diabetic retinopathy, glaucoma, diabetic macular degeneration and age-related macular degeneration. On the other hand, several worldwide challenges have shared big eye imaging datasets with segmentation of part of the eyes, clinical signs and the ocular diagnostic performed by experts. In addition, these methods are breaking the stigma of black-box models, with the delivering of interpretable clinically information. This review provides an overview of the state-of-the-art deep learning methods used in ophthalmic images, databases and potential challenges for ocular diagnosis

Automatic Visual Acuity Estimation by Means of Computational Vascularity Biomarkers Using Oct Angiographies.

Optical Coherence Tomography Angiography (OCTA) constitutes a new non-invasive ophthalmic image modality that allows the precise visualization of the micro-retinal vascularity that is commonly used to analyze the foveal region. Given that there are many systemic and eye diseases that affect the eye fundus and its vascularity, the analysis of that region is crucial to diagnose and estimate the vision loss. The Visual Acuity (VA) is typically measured manually, implying an exhaustive and time-consuming procedure. In this work, we propose a method that exploits the information of the OCTA images to automatically estimate the VA with an accurate error of 0.1713.

Artificial intelligence for pediatric ophthalmology.

Despite the impressive results of recent artificial intelligence applications to general ophthalmology, comparatively less progress has been made toward solving problems in pediatric ophthalmology using similar techniques. This article discusses the unique needs of pediatric patients and how artificial intelligence techniques can address these challenges, surveys recent applications to pediatric ophthalmology, and discusses future directions. The most significant advances involve the automated detection of retinopathy of prematurity, yielding results that rival experts. Machine learning has also been applied to the classification of pediatric cataracts, prediction of postoperative complications following cataract surgery, detection of strabismus and refractive error, prediction of future high myopia, and diagnosis of reading disability. In addition, machine learning techniques have been used for the study of visual development, vessel segmentation in pediatric fundus images, and ophthalmic image synthesis. Artificial intelligence applications could significantly benefit clinical care by optimizing disease detection and grading, broadening access to care, furthering scientific discovery, and improving clinical efficiency. These methods need to match or surpass physician performance in clinical trials before deployment with patients. Owing to the widespread use of closed-access data sets and software implementations, it is difficult to directly compare the performance of these approaches, and reproducibility is poor. Open-access data sets and software could alleviate these issues and encourage further applications to pediatric ophthalmology.

Ophthalmologists on Smartphones: Image-Based Teleconsultation.

Background:Teleophthalmology has the potential to facilitate wider access to expert advice. It includes viewing of ophthalmic images by experts either on handheld devices like smartphones/tablets or office devices such as computer screens. However, to ensure rapid feedback, the turnaround time of any consultation must be kept to a minimum which requires use of handheld user-friendly devices. The purpose of this study was to assess whether images of different eye ailments viewed on smartphones and tablets are of comparable subjective quality as those viewed on a computer screen.Methods:This was a prospective study comparing the subjective quality of images on a smartphone, tablet and computer screen. Thirty images were analysed – 10 of extraocular morphology, 10 of the anterior segment pathology and 10 of retinal diseases. Ten ophthalmologists participated and were instructed to rate the overall quality of each image on a 7-point Likert scale (terrible-1, poor-2, average-3, fair-4, good-5, very good-6, excellent-7).Results:Overall smartphones were found to have higher ratings of subjective image quality (5.9 ± 0.48) than images displayed on tablets (5.13 ± 0.51) and computers (5.0 ± 0.37). The images were rated ‘good’ or ‘very good’ in all (100%) of the smartphone images. Fundus images and extraocular images were rated higher than anterior segment images on the smartphone. When comparing the two handheld devices with computers, both smartphones and tablets had similar image quality (p > 0.05, not significant) to computer images. However, for extraocular diseases, smartphone (6.1 ± 0.32) had significantly better image quality and images were easier to interpret compared to images on the computer (p < 0.05).Smartphones were rated ‘very good’ in 88.33% cases. All consultants (n = 10) were comfortable with the use of smartphone images and were already using it for teleconsultation at least three times in a month. Vision technicians reported minimum delay in getting advice when sending the images on mobile application to expert ophthalmologists.Conclusion:Smartphones can be used for teleconsultation. Subjective qualities of ophthalmic images on a smartphone are similar to those on tablets and computers. For rural communities that rely on teleconsultation, this small study provides useful evidence which may support the use of smartphones, tablets or computers for viewing ophthalmic images.

An Interpretable and Expandable Deep Learning Diagnostic System for Multiple Ocular Diseases: Qualitative Study.

BackgroundAlthough artificial intelligence performs promisingly in medicine, few automatic disease diagnosis platforms can clearly explain why a specific medical decision is made.ObjectiveWe aimed to devise and develop an interpretable and expandable diagnosis framework for automatically diagnosing multiple ocular diseases and providing treatment recommendations for the particular illness of a specific patient.MethodsAs the diagnosis of ocular diseases highly depends on observing medical images, we chose ophthalmic images as research material. All medical images were labeled to 4 types of diseases or normal (total 5 classes); each image was decomposed into different parts according to the anatomical knowledge and then annotated. This process yields the positions and primary information on different anatomical parts and foci observed in medical images, thereby bridging the gap between medical image and diagnostic process. Next, we applied images and the information produced during the annotation process to implement an interpretable and expandable automatic diagnostic framework with deep learning.ResultsThis diagnosis framework comprises 4 stages. The first stage identifies the type of disease (identification accuracy, 93%). The second stage localizes the anatomical parts and foci of the eye (localization accuracy: images under natural light without fluorescein sodium eye drops, 82%; images under cobalt blue light or natural light with fluorescein sodium eye drops, 90%). The third stage carefully classifies the specific condition of each anatomical part or focus with the result from the second stage (average accuracy for multiple classification problems, 79%-98%). The last stage provides treatment advice according to medical experience and artificial intelligence, which is merely involved with pterygium (accuracy, >95%). Based on this, we developed a telemedical system that can show detailed reasons for a particular diagnosis to doctors and patients to help doctors with medical decision making. This system can carefully analyze medical images and provide treatment advices according to the analysis results and consultation between a doctor and a patient.ConclusionsThe interpretable and expandable medical artificial intelligence platform was successfully built; this system can identify the disease, distinguish different anatomical parts and foci, discern the diagnostic information relevant to the diagnosis of diseases, and provide treatment suggestions. During this process, the whole diagnostic flow becomes clear and understandable to both doctors and their patients. Moreover, other diseases can be seamlessly integrated into this system without any influence on existing modules or diseases. Furthermore, this framework can assist in the clinical training of junior doctors. Owing to the rare high-grade medical resource, it is impossible that everyone receives high-quality professional diagnosis and treatment service. This framework can not only be applied in hospitals with insufficient medical resources to decrease the pressure on experienced doctors but also deployed in remote areas to help doctors diagnose common ocular diseases.

OIPAV: an Integrated Software System for Ophthalmic Image Processing, Analysis, and Visualization.

Ophthalmic medical images, such as optical coherence tomography (OCT) images and color photo of fundus, provide valuable information for clinical diagnosis and treatment of ophthalmic diseases. In this paper, we introduce a software system specially oriented to ophthalmic images processing, analysis, and visualization (OIPAV) to assist users. OIPAV is a cross-platform system built on a set of powerful and widely used toolkit libraries. Based on the plugin mechanism, the system has an extensible framework. It provides rich functionalities including data I/O, image processing, interaction, ophthalmic diseases detection, data analysis, and visualization. By using OIPAV, users can easily access to the ophthalmic image data manufactured from different imaging devices, facilitate workflows of processing ophthalmic images, and improve quantitative evaluations. With a satisfying function scalability and expandability, the software is applicable for both ophthalmic researchers and clinicians.

BGIDB: A fundus ground truth building tool with automatic DDLS classification for glaucoma research

Taking advantage of the new standard HTML5, we designed an online tool called a browser/server-based glaucoma image database builder (BGIDB) for the demarcation of the optic disk and cup’s ellipse-like boundaries. The B-spline interpolation algorithm is used, and a specially designed algorithm is proposed for classifying the disease grade according to the disc damage likelihood scale criterion, which is correlated strongly with the glaucoma process by quantity. This tool exhibits the best performance with a low overlapping error of 4.34% for the optic disk demarcation and 8.31% for the optic cup demarcation. It also has preferable time-consuming as compared to other tools and is a cross-platform system. This tool has already been utilized in building the ophthalmic image database in the cooperation of Center for Ophthalmic Imaging Research and The Second Xiangya Hospital.

Fast and effective optic disk localization based on convolutional neural network

As a benchmark structure in the retina, the precise localization of the Optic Disc (OD) has received considerable attention from researchers owning to its importance for ophthalmic image analysis and retinopathy screening. In most literature works, although OD localization has achieved fairly good performance, rather less attention has been paid to supervised techniques. As the ODs are common in characteristics and form a fixed pattern, we propose in this paper an OD localization method based on Convolutional Neural Networks (CNNs). In data preparation, the blue channel in the fundus image, which is always empty or noisy and tends to be uninformative, is replaced by coarsely segmented vasculature maps (Red channel, Green channel and vasculatures are denoted as RGV). In addition, the input of the CNN structures is rectangular instead of square in order to involve more context information of the vasculatures. For training, a two-stage process is designed to alleviate the class-imbalance problem by choosing large number of positive samples at the first stage and choosing samples at the center of OD to fine-tune the fist-stage model at the second stage. Then a probability guided search algorithm is developed to improve the efficiency of OD localization by selectively searching patches with large chances to be an OD and their neighbors. Finally, the precise OD position is located as center of the highest probability regions after weighted voting. Extensive experiments on four publicly available databases demonstrate the effectiveness and efficiency of the proposed method, with an average detection rate of 99.11% and detection time less than 15 s per image.

Prevalence of Hepatocyte Growth Factor and Autoantibodies to α-HGF as a New Etiology for Bilateral Diffuse Uveal Melanocytic Proliferation Masquerading as Neovascular Age-Related Macular Degeneration.

Objective:The goal was to test the hypothesis that high serum hepatocyte growth factor (HGF) and retinal autoantibodies against α-HGF contribute to the pathology of bilateral diffuse melanocytic proliferation (BDUMP).Methods:Case report of an elderly diagnosed with neovascular age-related macular degeneration (n-AMD) treated with bilateral Bevacizumab injections. Examination included comprehensive ophthalmic examination and images obtained by fundus photography, fundus autofluorescence, fluorescein angiography, spectral-domain optical coherence tomography (OCT), and B-scan ultrasonography. The levels of HGF and circulating HGF receptor (c-MET) were measured in the serum by ELISA and anti-retinal autoantibodies by western blotting.Results:Patient received Bevacizumab injections for presumed n-AMD and had a history of papillary renal cell carcinoma stage 4 with a tumor containing gene mutation Y1230C in the mesenchymal-epithelial transition factor (MET). Visual acuity was 20/200 OD and CF OS. Multimodal imaging was consistent with BDUMP. Plasma exchange therapy was recommended but could not be started until 10 months later due to deterioration in his medical condition. Pre- and post-plasma exchange sera demonstrated anti-retinal autoantibodies against 69-kDa protein of the same molecular weight as the α-HGF. Serum autoantibodies reacted with purified recombinant α-HGF on the blot.Conclusions:BDUMP can mimic n-AMD, which can delay treatment. Plasma exchange resulted in resolved inflammation, resolution of exudative detachments and improved vision after cataract surgery. Consideration of the tumor genetics led to the recognition of elevated HGF levels and autoantibodies to α-HGF (anti-69-kDa), which suggested a new pathogenic mechanism of BDUMP. We believe that therapy with tyrosine kinase inhibitors and a checkpoint inhibitor may contribute to the high HGF levels and subsequent immune response.

Professor Tunde Peto: the role of new imaging modalities in the screening of diabetics retinopathy

Dr. Tunde Peto ( Figure 1 ) is Head of the Ophthalmic Image Reading Centre at Moorfields Eye Hospital and the Professor of Clinical Ophthalmology at Queen’s University Belfast. The Reading Centre is involved in screening, epidemiological studies and in clinical trials. It is also involved in mapping out new imaging possibilities where none existed before. Dr. Tunde Peto is an ophthalmologist with special research interest in chronic blinding diseases. She trained as an ophthalmologist and then completed her PhD in epidemiology and statistics on the field of diabetes care.

Analysis of yield of retinal imaging in a rural diabetes eye care model.

Purpose:The aim of this study is to analyze the yield of retinal images obtained in a rural diabetes eye care model.Methods:An analysis of a sample of nonmydriatic fundus photography (NMFP) of posterior segment ophthalmic images, obtained by an indigenous equipment (3 nethra-Forus Royal), was done in a district-wide rural diabetic retinopathy (DR) screening program; a trained optometrist did the initial image grading. DR and diabetic macular edema (DME) were classified based on international DR and DME severity scale. The agreement between the optometrist and retina specialist was very good (κ = 0.932; standard error = 0.030; 95% confidence interval = 0.874–0.991).Results:Posterior segment images of 2000 eyes of 1000 people with diabetes mellitus (DM) were graded. The mean age of the participants was 55.7 ± 11.5 standard deviation years. Nearly 42% of the screened participants (n = 420/1000) needed referral. The most common referable posterior segment abnormality was DR (8.2%). The proportion of people with any form of DR was seen in 110/1225 eyes, and sight-threatening DR was seen in 35/1225 eyes. About 62% of posterior segment images were gradable. The reasons for ungradable posterior segment images (34%) were small pupil, unfocused/partially available field of images, and cataract.Conclusion:A NMFP model was able to detect referable posterior segment abnormalities in a rural diabetes eye care program. Reasons found for ungradability of images in the present study can be addressed while designing future DR screening programs in the rural areas.

Automatic diagnosis of imbalanced ophthalmic images using a cost-sensitive deep convolutional neural network

BackgroundOcular images play an essential role in ophthalmological diagnoses. Having an imbalanced dataset is an inevitable issue in automated ocular diseases diagnosis; the scarcity of positive samples always tends to result in the misdiagnosis of severe patients during the classification task. Exploring an effective computer-aided diagnostic method to deal with imbalanced ophthalmological dataset is crucial.MethodsIn this paper, we develop an effective cost-sensitive deep residual convolutional neural network (CS-ResCNN) classifier to diagnose ophthalmic diseases using retro-illumination images. First, the regions of interest (crystalline lens) are automatically identified via twice-applied Canny detection and Hough transformation. Then, the localized zones are fed into the CS-ResCNN to extract high-level features for subsequent use in automatic diagnosis. Second, the impacts of cost factors on the CS-ResCNN are further analyzed using a grid-search procedure to verify that our proposed system is robust and efficient.ResultsQualitative analyses and quantitative experimental results demonstrate that our proposed method outperforms other conventional approaches and offers exceptional mean accuracy (92.24%), specificity (93.19%), sensitivity (89.66%) and AUC (97.11%) results. Moreover, the sensitivity of the CS-ResCNN is enhanced by over 13.6% compared to the native CNN method.ConclusionOur study provides a practical strategy for addressing imbalanced ophthalmological datasets and has the potential to be applied to other medical images. The developed and deployed CS-ResCNN could serve as computer-aided diagnosis software for ophthalmologists in clinical application.

Professor Tunde Peto: the role of new imaging modalities in the screening of diabetics retinopathy

Dr. Tunde Peto ( Figure 1 ) is Head of the Ophthalmic Image Reading Centre at Moorfields Eye Hospital and the Professor of Clinical Ophthalmology at Queen’s University Belfast. The Reading Centre is involved in screening, epidemiological studies and in clinical trials. It is also involved in mapping out new imaging possibilities where none existed before. Dr. Tunde Peto is an ophthalmologist with special research interest in chronic blinding diseases. She trained as an ophthalmologist and then completed her PhD in epidemiology and statistics on the field of diabetes care.

Comparative analysis of image classification methods for automatic diagnosis of ophthalmic images

There are many image classification methods, but it remains unclear which methods are most helpful for analyzing and intelligently identifying ophthalmic images. We select representative slit-lamp images which show the complexity of ocular images as research material to compare image classification algorithms for diagnosing ophthalmic diseases. To facilitate this study, some feature extraction algorithms and classifiers are combined to automatic diagnose pediatric cataract with same dataset and then their performance are compared using multiple criteria. This comparative study reveals the general characteristics of the existing methods for automatic identification of ophthalmic images and provides new insights into the strengths and shortcomings of these methods. The relevant methods (local binary pattern +SVMs, wavelet transformation +SVMs) which achieve an average accuracy of 87% and can be adopted in specific situations to aid doctors in preliminarily disease screening. Furthermore, some methods requiring fewer computational resources and less time could be applied in remote places or mobile devices to assist individuals in understanding the condition of their body. In addition, it would be helpful to accelerate the development of innovative approaches and to apply these methods to assist doctors in diagnosing ophthalmic disease.

Electronic Referrals and Digital Imaging Systems in Ophthalmology: A Global Perspective.

Ophthalmology departments face intensifying pressure to expedite sight-saving treatments and reduce the global burden of disease. The use of electronic communication systems, digital imaging, and redesigned service care models is imperative for addressing such demands. The recently developed Scottish Eyecare Integration Project involves an electronic referral system from community optometry to the hospital ophthalmology department using National Health Service (NHS) email with digital ophthalmic images attached, via a virtual private network connection. The benefits over the previous system include reduced waiting times, improved triage, e-diagnosis in 20% without the need for hospital attendance, and rapid electronic feedback to referrers. We draw on the experience of the Scottish Eyecare Integration Project and discuss the global applications of this and other advances in teleophthalmology. We focus particularly on the implications for management and screening of chronic disease, such as glaucoma and diabetic eye disease, and ophthalmic disease, such as retinopathy of prematurity where diagnosis is almost entirely and critically dependent on fundus appearance. Currently in Scotland, approximately 75% of all referrals are electronic from community to hospital. The Scottish Eyecare Integration Project is globally the first of its kind and unique in a national health service. Such speedy, safe, and efficient models of communication are geographically sensitive to service provision, especially in remote and rural regions. Along with advances in teleophthalmology, such systems promote the earlier detection of sight-threatening disease and safe follow-up of non-sight-threatening disease in the community.